© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 1810
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and crime-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nuages
    -0.78
     marquées
    -0.71
     createState
    -0.71
     juridiques
    -0.70
     gomma
    -0.70
     chrétiens
    -0.69
     peggio
    -0.66
     gambe
    -0.66
     للاسماء
    -0.66
     démission
    -0.65
    POSITIVE LOGITS
     organization
    0.71
     system
    0.63
     systems
    0.63
     affair
    0.62
     organisation
    0.62
     division
    0.61
     mode
    0.59
     operations
    0.58
    zungs
    0.58
     surla
    0.58
    Activations Density 1.365%

    No Known Activations